{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:27:09Z","timestamp":1784644029053,"version":"3.55.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2403297,2144194"],"award-info":[{"award-number":["2403297,2144194"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127989","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13226-13233","source":"Crossref","is-referenced-by-count":11,"title":["EgoMimic: Scaling Imitation Learning via Egocentric Video"],"prefix":"10.1109","author":[{"given":"Simar","family":"Kareer","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Patel","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Punamiya","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranay","family":"Mathur","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Judy","family":"Hoffman","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.016","volume-title":"Learning fine-grained bimanual manipulation with low-cost hardware","author":"Zhao","year":"2023"},{"key":"ref2","volume-title":"Aloha 2: An enhanced low-cost hardware for bimanual teleoperation","author":"Team","year":"2024"},{"key":"ref3","volume-title":"Gello: A general, low-cost, and intuitive teleoperation framework for robot manipulators","author":"Wu","year":"2024"},{"key":"ref4","volume-title":"Universal manipulation interface: In-the-wild robot teaching without in-the-wild robots","author":"Chi","year":"2024"},{"key":"ref5","volume-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023"},{"key":"ref6","volume-title":"Towards generalizable zero-shot manipulation via translating human interaction plans","author":"Bharadhwaj","year":"2023"},{"key":"ref7","volume-title":"Project aria: A new tool for egocentric multi-modal ai research","author":"Engel","year":"2023"},{"key":"ref8","article-title":"Probabilistic movement primitives","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Paraschos","year":"2013"},{"key":"ref9","volume-title":"One-shot visual imitation learning via meta-learning","author":"Finn","year":"2017"},{"key":"ref10","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","volume-title":"Diffusion policy: Visuomotor policy learning via action diffusion","author":"Chi","year":"2024"},{"key":"ref12","author":"Young","year":"2020","journal-title":"Visual imitation made easy"},{"key":"ref13","volume-title":"Rt-1: Robotics transformer for real-world control at scale","author":"Brohan","year":"2023"},{"key":"ref14","volume-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref15","volume-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref16","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref17","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","volume-title":"Learning by watching: Physical imitation of manipulation skills from human videos","author":"Xiong","year":"2021"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.092","volume-title":"Any-point trajectory modeling for policy learning","author":"Wen","year":"2024"},{"key":"ref20","volume-title":"Track2act: Predicting point tracks from internet videos enables generalizable robot manipulation","author":"Bharadhwaj","year":"2024"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.01324","volume-title":"Affordances from human videos as a versatile representation for robotics","author":"Bahl","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1145\/3610977.3637486","article-title":"Using 3d mice to control robot manipulators","volume-title":"Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Dhat","year":"2024"},{"key":"ref24","volume-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","author":"Zhu","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160547"},{"key":"ref26","volume-title":"Openvr: Teleoperation for manipulation","author":"George","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013428"},{"key":"ref28","article-title":"Open-television: teleoperation with immersive active visual feedback","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Airexo: Low-cost exoskeletons for learning whole-arm manipulation in the wild","author":"Fang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Ace: A cross-platform visual-exoskeletons system for low-cost dexterous teleoperation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.052"},{"key":"ref34","article-title":"Humanplus: Humanoid shadowing and imitation from humans","volume-title":"Conference on Robot Learning (CoRL)","author":"Fu","year":"2024"},{"key":"ref35","article-title":"On bringing robots home","author":"Shafiullah","journal-title":"arXiv preprint"},{"key":"ref36","volume-title":"Dexcap: Scalable and portable mocap data collection system for dexterous manipulation","author":"Wang","year":"2024"},{"key":"ref37","article-title":"R+ x: Re-trieval and execution from everyday human videos","author":"Papagiannis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01834"},{"key":"ref39","volume-title":"Ego4d: Around the world in 3,000 hours of egocentric video","author":"Grauman","year":"2022"},{"key":"ref40","volume-title":"Nymeria: A massive collection of multimodal egocentric daily motion in the wild","author":"Ma","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3138382"},{"key":"ref42","volume-title":"Basics - project aria docs","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.093"},{"key":"ref44","article-title":"Re-mix: Optimizing data mixtures for large scale imitation learning","author":"Hejna","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2021.XVII.002","volume-title":"Manipulator-independent representations for visual imitation","author":"Zhou","year":"2021"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2022.XVIII.026","volume-title":"Human-to-robot imitation in the wild","author":"Bahl","year":"2022"},{"key":"ref47","volume-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127989.pdf?arnumber=11127989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:46:24Z","timestamp":1756881984000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127989","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}